神经网络在气动PWM位置伺服系统中的应用

将递归神经网络对于阶未知的非线性对象或具有未知延迟的系统辨识能力与ＰＩＤ控制的有效性相结合，构成了一种基于递归神经网络的自适应ＰＩＤ控制系统，对气动脉宽调制位置伺服系统进行控制，使系统获得了一定的在线自我调整能力，提高了系统的性能。     

Theoretical and Experimental Research on the Sound Field in A Finite Duct

Based upon the theoretical analysis of the sound field in a finite duct and the spatialsampling principle,this paper applies the adaptive filtering technique to the measurement of thesound field in the duct with the distribution patterns of standing waves in the direction of thewaveguide and high—order wavefront on the cross section of the duct measured and the acousticmode theory proved by experimental results.     

神经网络自适应滤波器

本文介绍一种新颖的非线性自逅应滤波器——自适应神经网络滤波器.由于神经网络具有学习非线性函数到任意的精度以及自适应能力,这种滤波器优于线性滤波器,能适应各种噪声环境.在自适应LMS算法基础上,提出了在线PB训练算法、收敛速度快.最后以自适应噪声对消系统为例,进行了计算机仿真,结果显示了这种滤波器的良好性能.     

二阶变结构自适应控制系统的设计

介绍了一种只有一个时变参数的自适应变结构控制方案．该方案简单易行．且有一定的实际应用价值．     

AMT 模糊自适应滤波技术

信息处理技术是实现车辆起步控制的关键。对于转速脉冲信号，因为包含高频过零脉冲，其滤波十分困难，为此本文引入模糊推理技术，采用人工智能的方法进行自适应滤波。实验证明其滤波效果十分明显。     

神经网络非线性系统自适应控制的研究

提出了一种新的神经网络非线性系统自适应控制方法采用改进的ＢＰ算法，避免了选取学习速率的麻烦仿真结果表明：该方法对非线性系统及突加外干拢、参数突变具有较强的自适应能力     

Discrete Adaptive Sliding Mode Control of a State-Space System with a Bounded Disturbance

This paper presents the discrete adaptive sliding mode control of a state-space system in the presence of a bounded disturbance. The delta form of the discrete state-space model is used as it closely resembles that of the continuous model. The control law takes into account of the effect of the disturbance by using its approximate value. The system behavior in the vicinity of the sliding surface is studied. It is shown that the adaptive controller leads to a stable closed-loop system. Also, simulation results are presented to illustrate the features of the proposed adaptive control strategy.     

Adaptive Variable Structure Control Design for Uncertain Time-Delayed Systems with Nonlinear Input

This paper presents a new robust control for uncertain dynamic time-delayed systems with series nonlinearities. It is implemented by using variable structure control. The proposed variable structure controller ensures the global reaching condition of the sliding mode of the uncertain time-delayed system. However, in the sliding mode, the investigated uncertain time-delayed system still bears the insensitivity to the uncertainties and disturbances as the systems with linear input. Furthermore, the proposed controller is achieved through adaptive variable structure control without the limitation of knowing the bounds of the uncertainties and perturbations in advance.     

Qos-aware Middleware for Mobile Multimedia Communications

Next generation wireless communications system will be required to support the seamless delivery of voice, video and data with high quality. Delivering hard Quality of Service (QOS) assurances in the wireless domain is complex due to large-scale mobility requirements, limited radio resources and fluctuating network conditions. To address this challenge we are developing mobiware, a QOS-aware middleware platform that contains the complexity of supporting multimedia applications operating over wireless and mobile networks. Mobiware is a highly programmable software platform based on the latest distributed systems technology (viz. CORBA and Java). It is designed to operate between the application and radio-link layers of next generation wireless and mobile systems. Mobiware provides value-added QOS support by allowing mobile multimedia applications to operate transparently during handoff and periods of persistent QOS fluctuation.     

一种改进型快速BP训练算法

本文以自适应步长调整代替ＤＦＰ优化方法中的一维搜索，并将它应用于前馈神经网络训练中。同时对步长的衰减因子和增长因子进行动态自适应调整，提高了ＢＰ训练算法的收敛速度和摆脱局部极小的能力，实验结果证明了该算法的有效性。